Developing a Method to Detect Indoor Spatial Entities in Omnidirectional Images for Constructing IndoorGML Data

다국어 초록 (Multilingual Abstract)

The continuous increase in interest in indoor space demands the development of LBSs (Location Based Services) for navigation, routing, and space query in these environments. Applications providing these services must use visualization and topology data together to provide relevant services to users. Applications have frequently used geometric object-based visualization models for indoor space LBSs. These have the advantage of being easy to use with IndoorGML, an indoor topology model, but have the disadvantage of high construction cost and heavy data. Correspondingly, the image-based visualization model drew attention as an alternative model. However, using such models requires identifying objects on the image to be used alongside IndoorGML, presenting a limitation because it is difficult to identify objects in the image pixels directly. To overcome the limitations of image-based visualization models and reconsider the usability of indoor space LBS using images, this study presents a method to automatically detect spatial objects required to construct IndoorGML from images using deep learning. This methodology aims to detect objects mainly used in indoor LBSs, which include door and stair objects portrayed in indoor omnidirectional images. This study proposes a detailed method of constructing a training dataset for indoor spatial object detection. Moreover, this research presents a method of refining the training dataset and directly acquiring omnidirectional image data to train it as an object detection model that can be used universally in various buildings while maintaining compliant accuracy.

참고문헌 (Reference)

1 김문수 ; 강혜영 ; 이지영, "영상 데이터를 활용한 실내 토폴로지 구현에 관한 연구" 한국측량학회 34 (34): 329-338, 2016

2 이기준 ; 이지영, "실내공간 표준안 IndoorGML의 개념 및 활용" 대한공간정보학회 21 (21): 1-10, 2013

3 강혜영 ; 이지영, "실내공간 데이터 기반의 응용 서비스를 위한 세밀도 모델에 관한 연구" 한국측량학회 32 (32): 143-151, 2014

4 류정림 ; 문선기 ; 추승연, "개방형 BIM 기반 IFC 모델을 이용한 실내공간정보 시각화 도구개발 및 활용방안 연구" 대한공간정보학회 23 (23): 41-52, 2015

5 Redmon, J., "You only look once: Unified, real-time object detection" 2 : 779-788, 2016

6 Bochkovskiy, A., "YOLOv4: Optimal speed and accuracy of object detection"

7 Claridades, Alexis Richard ; 이지영 ; Blanco, Ariel, "Using Omnidirectional Images for Semi-Automatically Generating IndoorGML Data" 한국측량학회 36 (36): 319-333, 2018

8 He, K., "Spatial pyramid pooling in deep convolutional networks for visual recognition" 37 (37): 1904-1916, 2015

9 Liu, S., "Path aggregation network for instance segmentation" 1 : 8759-8768, 2018

10 The Construction Specifications Institute, "OmniClassa®- A strategy for classifying the built environment, Edition: 2.1"

11 The Construction Specifications Institute, "OmniClass - A strategy for classifying the built environmemt; Table 23-Products, National Standard 2012-05-16"

12 Hernandez, A. C., "Object detection applied to indoor environments for mobile robot navigation" 16 (16): 1180-, 2016

13 Ahn, D., "Integrating image and network-based topological data through spatial data fusion for indoor location-based services" 2020 : 8877739-887750, 2020

14 Open Geospatial Consortium, "IndoorGML v.1.0.3, Document Number 14-005r5"

15 Afif, M., "Indoor objects detection and recognition for an ICT mobility assistance of visually impaired people" 79 : 31645-61662, 2020

16 Jung, H., "Development of Indoor Space Application Data Model Based on Integrating IndoorGML with 3D Image-Focusing on Patrol Service" University of Seoul 2016

17 Claridades, A. R. C., "Developing a data fusion sterategy between omnidirctional image and IndoorGML data, The International Archives of the Photogrammetry" XLII-4/W19 : 117-124, 2019

18 Lecrosnier, L., "Deep learning-based object detection, localisation and tracking for smart wheelchair healthcare mobility" 18 (18): 91-, 2020

19 Liu, L., "Deep learning for generic object detection : A survey" 128 : 261-318, 2020

20 Wang, H., "Deep learning based target detection algorithm for motion capture applications" 1-6, 2020

21 Wang, C., "CSPNet : A new backbone that can enhance learning capability of CNN" 390-391, 2020

22 Padilla, R., "A survey on performance metrics for object-detection algorithms" 237-242, 2020

23 Jiao, L., "A survey of deep learning-based object detection" 7 : 128837-128868, 2019

24 Claridades, A. R. C., "3D visualization of building interior using omnidirectional images" 2244-2253, 2018